{"id":"https://openalex.org/W2122590558","doi":"https://doi.org/10.1186/s13321-014-0040-8","title":"A document classifier for medicinal chemistry publications trained on the ChEMBL corpus","display_name":"A document classifier for medicinal chemistry publications trained on the ChEMBL corpus","publication_year":2014,"publication_date":"2014-08-11","ids":{"openalex":"https://openalex.org/W2122590558","doi":"https://doi.org/10.1186/s13321-014-0040-8","mag":"2122590558","pmid":"https://pubmed.ncbi.nlm.nih.gov/25221627"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-014-0040-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-014-0040-8","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-014-0040-8","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-014-0040-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065497953","display_name":"George Papadatos","orcid":"https://orcid.org/0000-0002-8314-7061"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"George Papadatos","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD UK","European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Hinxton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD UK","institution_ids":["https://openalex.org/I1303153112"]},{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Hinxton, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088996741","display_name":"Gerard J. P. van Westen","orcid":"https://orcid.org/0000-0003-0717-1817"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Gerard JP van Westen","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD UK","European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Hinxton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD UK","institution_ids":["https://openalex.org/I1303153112"]},{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Hinxton, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050861360","display_name":"Samuel Croset","orcid":"https://orcid.org/0000-0002-9591-0060"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Samuel Croset","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD UK","European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Hinxton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD UK","institution_ids":["https://openalex.org/I1303153112"]},{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Hinxton, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055698340","display_name":"Rita Santos","orcid":"https://orcid.org/0000-0002-5431-4756"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rita Santos","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD UK","European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Hinxton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD UK","institution_ids":["https://openalex.org/I1303153112"]},{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Hinxton, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009144971","display_name":"Simone Trubian","orcid":null},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simone Trubian","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD UK","European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Hinxton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD UK","institution_ids":["https://openalex.org/I1303153112"]},{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Hinxton, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001723208","display_name":"John P. Overington","orcid":"https://orcid.org/0000-0002-5859-1064"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"John P Overington","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD UK","European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Hinxton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD UK","institution_ids":["https://openalex.org/I1303153112"]},{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), European Molecular Biology Laboratory, Hinxton, UK","institution_ids":["https://openalex.org/I1303153112"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5088996741"],"corresponding_institution_ids":["https://openalex.org/I1303153112"],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":2190,"currency":"USD","value_usd":2190},"fwci":0.52,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.64896638,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"6","issue":"1","first_page":"40","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9121999740600586,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9121999740600586,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.05339999869465828,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.005799999926239252,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/chembl","display_name":"chEMBL","score":0.9621726274490356},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7882146835327148},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7242817878723145},{"id":"https://openalex.org/keywords/file-transfer-protocol","display_name":"File Transfer Protocol","score":0.6882069110870361},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5841977596282959},{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.5153681635856628},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.507434070110321},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.461130291223526},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.446293443441391},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.41168728470802307},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3798239827156067},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.37362560629844666},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2952442169189453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.263507217168808},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.2402135133743286},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.22762641310691833},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.16889911890029907}],"concepts":[{"id":"https://openalex.org/C63222358","wikidata":"https://www.wikidata.org/wiki/Q6120337","display_name":"chEMBL","level":3,"score":0.9621726274490356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7882146835327148},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7242817878723145},{"id":"https://openalex.org/C169485995","wikidata":"https://www.wikidata.org/wiki/Q42283","display_name":"File Transfer Protocol","level":3,"score":0.6882069110870361},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5841977596282959},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.5153681635856628},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.507434070110321},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.461130291223526},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.446293443441391},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41168728470802307},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3798239827156067},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.37362560629844666},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2952442169189453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.263507217168808},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2402135133743286},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.22762641310691833},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.16889911890029907},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13321-014-0040-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-014-0040-8","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-014-0040-8","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:25221627","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25221627","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of cheminformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:4158272","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4158272","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"J Cheminform","raw_type":"Text"},{"id":"pmh:oai:openaccess.leidenuniv.nl:1887/133511","is_oa":true,"landing_page_url":"http://hdl.handle.net/1887/133511","pdf_url":null,"source":{"id":"https://openalex.org/S4306400850","display_name":"Leiden Repository (Leiden University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I121797337","host_organization_name":"Leiden University","host_organization_lineage":["https://openalex.org/I121797337"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"6","raw_type":"Article / Letter to editor"},{"id":"pmh:oai:scholarlypublications.universiteitleiden.nl:item_2872970","is_oa":true,"landing_page_url":"https://hdl.handle.net/1887/133511","pdf_url":null,"source":{"id":"https://openalex.org/S4306400850","display_name":"Leiden Repository (Leiden University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I121797337","host_organization_name":"Leiden University","host_organization_lineage":["https://openalex.org/I121797337"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics","raw_type":"Article / Letter to editor"}],"best_oa_location":{"id":"doi:10.1186/s13321-014-0040-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-014-0040-8","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-014-0040-8","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1499650114","display_name":"The ChEMBL Database An Open Resource for Drug Discovery","funder_award_id":"104104","funder_id":"https://openalex.org/F4320311904","funder_display_name":"Wellcome Trust"},{"id":"https://openalex.org/G2154574704","display_name":"Alignment of Synthesis, Medicinal Chemistry and Structural Genomics to Accelerate UK Drug Discovery: Network SMS-Drug","funder_award_id":"EP/I037229/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5684441142","display_name":null,"funder_award_id":"WT086151/Z/08/Z","funder_id":"https://openalex.org/F4320311904","funder_display_name":"Wellcome Trust"},{"id":"https://openalex.org/G5801879276","display_name":null,"funder_award_id":"EP/I037229/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320311904","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2122590558.pdf","grobid_xml":"https://content.openalex.org/works/W2122590558.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1835740130","https://openalex.org/W1969623908","https://openalex.org/W1975875968","https://openalex.org/W1976097579","https://openalex.org/W1978350006","https://openalex.org/W2032729847","https://openalex.org/W2096864392","https://openalex.org/W2101553882","https://openalex.org/W2140785063","https://openalex.org/W2142425999","https://openalex.org/W2142741334","https://openalex.org/W2148083369","https://openalex.org/W2165671627","https://openalex.org/W2911964244"],"related_works":["https://openalex.org/W2780675302","https://openalex.org/W4294024451","https://openalex.org/W4207063555","https://openalex.org/W2803206732","https://openalex.org/W2585302987","https://openalex.org/W1964657534","https://openalex.org/W2431109715","https://openalex.org/W2472085920","https://openalex.org/W2070692310","https://openalex.org/W4200184670"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,81,114,183],"large":[2,231],"increase":[3],"in":[4,22,26,177,225,236],"the":[5,27,85,92,104,198,201,234,237,244],"number":[6],"of":[7,84,94,200],"scientific":[8,202],"publications":[9,58],"has":[10,116],"fuelled":[11],"a":[12,48,107,120],"need":[13],"for":[14,31,36,110,123,171],"semi-":[15],"and":[16,34,40,69,76,97,101,129,136,169,223,241],"fully":[17],"automated":[18],"text":[19,111],"mining":[20],"approaches":[21],"order":[23],"to":[24,54,64,71,99,148,153,165,204,207,217],"assist":[25],"triage":[28],"process,":[29],"both":[30,124],"individual":[32],"scientists":[33],"also":[35],"larger-scale":[37],"data":[38,121,190],"extraction":[39],"curation":[41,96],"into":[42],"public":[43],"databases.":[44],"Here,":[45],"we":[46,194],"introduce":[47],"document":[49,161,218],"classifier,":[50],"which":[51,193],"is":[52,230,248],"able":[53],"successfully":[55],"distinguish":[56],"between":[57,233],"that":[59,78],"are":[60,79,138,185],"'ChEMBL-like'":[61],"(i.e.":[62],"related":[63],"small":[65],"molecule":[66],"drug":[67],"discovery":[68],"likely":[70],"contain":[72],"quantitative":[73],"bioactivity":[74],"data)":[75],"those":[77],"not.":[80],"unprecedented":[82],"size":[83],"medicinal":[86],"chemistry":[87,100],"literature":[88],"collection,":[89],"coupled":[90],"with":[91],"advantage":[93],"manual":[95],"mapping":[98],"biology":[102],"make":[103],"ChEMBL":[105,239],"corpus":[106],"unique":[108],"resource":[109],"mining.":[112],"RESULTS:":[113],"method":[115],"been":[117],"implemented":[118],"as":[119,175],"protocol/workflow":[122],"Pipeline":[125],"Pilot":[126],"(version":[127,131],"8.5)":[128],"KNIME":[130],"2.9)":[132],"respectively.":[133],"Both":[134],"workflows":[135],"models":[137,184],"freely":[139],"available":[140,187],"at:":[141],"ftp://ftp.ebi.ac.uk/pub/databases/chembl/text-mining.":[142],"These":[143],"can":[144],"be":[145,166],"readily":[146,186],"modified":[147],"include":[149],"additional":[150],"keyword":[151],"constraints":[152],"further":[154],"focus":[155],"searches.":[156],"CONCLUSIONS:":[157],"Large-scale":[158],"machine":[159],"learning":[160],"classification":[162],"was":[163],"shown":[164],"very":[167],"robust":[168],"flexible":[170],"this":[172],"particular":[173],"application,":[174],"illustrated":[176],"four":[178],"distinct":[179],"text-mining-based":[180],"use":[181],"cases.":[182],"on":[188],"two":[189],"workflow":[191],"platforms,":[192],"believe":[195],"will":[196],"allow":[197],"majority":[199],"community":[203],"apply":[205],"them":[206],"their":[208],"own":[209],"data.":[210],"\u115f:":[211],"Graphical":[212],"AbstractMultidimensional":[213],"scaling":[214],"analysis":[215],"applied":[216],"vectors":[219],"derived":[220],"from":[221],"titles":[222],"abstracts":[224],"different":[226,238],"corpora.":[227],"Notably,":[228],"there":[229],"overlap":[232],"documents":[235],"versions":[240],"BindingDB,":[242],"while":[243],"background":[245],"MEDLINE":[246],"set":[247],"largely":[249],"divergent.":[250]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
